© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58750
    Prev
    Next
    INDEX
    Explanations

    The reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ॥
    -1.52
     illustratie
    -1.52
     and
    -1.46
    -1.42
    ecé
    -1.39
    鹟
    -1.38
    utriche
    -1.35
     ontdek
    -1.35
     &
    -1.34
    orology
    -1.34
    POSITIVE LOGITS
     наоборот
    1.31
     чтобы
    1.25
     других
    1.24
    lerde
    1.23
    Beij
    1.20
    larda
    1.20
     varsa
    1.20
     другие
    1.18
    reiz
    1.18
     ruines
    1.16
    Activations Density 0.001%
    No Known Activations